Hand Gesture Recognition

Using Hidden Markov Models

Shuang Lu, Amir Harati and Joseph Picone

Institute for Signal and Information ProcessingTemple UniversityPhiladelphia, Pennsylvania, USA

IEEE Northern Virginia Section May 29, 20132

Abstract

Advanced gaming interfaces have generated renewed interest in hand gesture recognition as an ideal interface for human computer interaction. In this talk, we will discuss a specific application of gesture recognition - fingerspelling in American Sign Language. Signer-independent (SI) fingerspelling alphabet recognition is a very challenging task due to a number of factors including the large number of similar gestures, hand orientation and cluttered background. We propose a novel framework that uses a two-level hidden Markov model (HMM) that can recognize each gesture as a sequence of sub-units and performs integrated segmentation and recognition. We present results on signer-dependent (SD) and signer-independent (SI) tasks for the ASL Fingerspelling Dataset: error rates of 2.0% and 46.8% respectively.

Nonlinear StatsMarch 25, 2009

The SequelMay 9, 2012

Part III – ImageMay 29, 2013

IEEE Northern Virginia Section May 29, 20133

Gesture Recognition… In The Movies…

• Emphasized the use of wireless data gloves to better localize hand positions.

• Manipulated data on a 2D screen.

• Relatively simple inventory of gestures focused on window manipulations.

• Integrated gestures and speech recognition to provide a very natural dialog.

• Introduced 3D visualization and object manipulation.

• Virtual reality-style CAD.

IEEE Northern Virginia Section May 29, 20134

• Microsoft Kinect Motion sensing input device for Xbox

(and Windows in 2014) 8-bit RGB camera 11-bit infrared depth sensor

(infrared laser projector and CMOS sensor) Multi-array microphone Frame rate of 9 to 30 Hz Resolution from 640x480 to 1280x1024

Gesture Recognition: Improved Sensors

3D Depth Sensors

RGB Camera

Motorized Tilt

Microphone Array

• Depth images are useful for separating the image from the background

• Wireframe modeling and other on-board signal processing provides high quality image tracking

IEEE Northern Virginia Section May 29, 20135

• Primary mode of communication for over 500,000 people in North America alone.

• Approximately 6,000 words with unique signs.

• Additional words are spelled using fingerspelling of alphabet signs.

• In a typical communication, 10% to 15% of the words are signed by fingerspelling of alphabet signs.

• Similar to written English, the one-handed Latin alphabet in ASL consists of 26 hand gestures.

• The objective of our work is to classify 24 ASL alphabet signs from a static 2D image (we exclude “J” and “Z” because they are dynamic hand gestures).

Gesture Recognition: American Sign Language (ASL)

IEEE Northern Virginia Section May 29, 20136

• Similar shapes(e.g., “r” vs. “u”)

• Separation of hand from background

• Hand and background are similar in color

• Hand and arm are similar in color

• Background occurs within a hand shape

• Left-handed vs. right-handed

• Rotation, magnification, perspective, lighting, complex backgrounds, skin color, …

• Signer independent (SI) vs.signer dependent (SD)

Gesture Recognition: ASL still a challenging problem

IEEE Northern Virginia Section May 29, 20137

Architecture: Two-Level Hidden Markov Model

IEEE Northern Virginia Section May 29, 20138

Architecture: Histogram of Oriented Gradient (HOG)

Benefits:

• Illumination invariance due to the normalization of the gradient of the intensity values within a window.

• Emphasizes edges by the use of an intensity gradient calculation.

• Less sensitive to background details because the features use a distribution rather than a spatially-organized signal.

• Gradient intensity and orientation:

• In every window, separate A(x, y) (from 0 to 2π) into 9 regions; sum all G(x, y) within the same region.

• Normalize features inside each block:

( , ) atan( ( , ) / ( , ))y xA x y G x y G x y

2 2( , ) ( , ) ( , )x yG x y G x y G x y

( , ) ( 1, ) ( 1, )xG x y I x y I x y ( , ) ( , 1) ( , 1)yG x y I x y I x y

IEEE Northern Virginia Section May 29, 20139

Architecture: Two-Levels of Hidden Markov Models

IEEE Northern Virginia Section May 29, 201310

Experiments: ASL Fingerspelling Corpus

• 24 static gestures (excluding letters ”J” and ”Z”)• 5 subsets from 4 subjects• More than 500 images per sign per subject• A total of 60,000 images

• Similar gestures

• Different image sizes

• Face occlusion

• Changes in illumination

• Variations in signers

• Sign rotation

IEEE Northern Virginia Section May 29, 201311

Experiments: Parameter Tuning

• Performance as a function of the frame/window size

Frame (N)

Window (M) % Overlap Error

(%)5 20 75% 7.1%5 30 83% 4.4%

10 20 50% 5.1%10 30 67% 5.0%10 60 83% 8.0%

System Parameter ValueFrame Size (pixels) 5Window Size (pixels) 30No. HOG Bins 9No. Sub-gesture Segments 11No. States Per Sub-gesture Model 21No. States Long Background (LB) 11No. States Short Background (SB) 1No. Gaussian Mixtures (SG models) 16No. Gaussian Mixtures (LB/SB models) 32

No. Mixtures

Error Rate (%)

1 9.92 6.84 4.48 2.9

16 2.0

• Performance as a function of the number of mixture components

• An overview of the optimal system parameters

• Parameters were sequentially optimized and then jointly varied to test for optimality

• Optimal settings are a function of the amount of data and magnification of the image

IEEE Northern Virginia Section May 29, 201312

Experiments: SD vs. SI Recognition

System SD Shared SI

Pugeault(Color Only) N/A 27.0% 65.0%

Pugeault(Color + Depth) N/A 25.0% 53.0%

HMM(Color Only) 2.0% 7.8% 46.8%

• Performance is relatively constant as a function of the cross-validation set

• Greater variation as a function of the subject

• SD performance is significantly better than SI performance.

• “Shared” is a closed-subject test where 50% of the data is used for training and the other 50% is used for testing.

• HMM performance doesn’t improve dramatically with depth.

IEEE Northern Virginia Section May 29, 201313

Experiments: Error Analysis

• Gestures with a high confusion error rate.

• Images with significant variations in background and hand rotation.

• “SB” model is not reliably detecting background.

• Solution: transcribed data?

IEEE Northern Virginia Section May 29, 201314

Analysis: ASL Fingerspelling Corpus

Recognition resultRegion of interest

IEEE Northern Virginia Section May 29, 201315

Summary and Future Directions

• A two-level HMM‑based ASL fingerspelling alphabet recognition system that trains gesture and background noise models automatically: Five essential parameters were tuned by cross-validation. Our best system configuration achieved a 2.0% error rate on an SD task,

and a 46.8% error rate on an SI task.

• Currently developing new architectures that perform improved segmentation. Both supervised and unsupervised methods will be employed. We expect performance to be significantly better on the SI task.

• All scripts, models, and data related to these experiments are available from our project web site:

http://www.isip.piconepress.com/projects/asl_fs.

IEEE Northern Virginia Section May 29, 201316

Brief Bibliography of Related Research

[1] Lu, S., & Picone, J. (2013). Fingerspelling Gesture Recognition Using Two Level Hidden Markov Model. Proceedings of the International Conference on Image Processing, Computer Vision, and Pattern Recognition. Las Vegas, USA. (Download).

[2] Pugeault, N. & Bowden, R. (2011). Spelling It Out: Real-time ASL Fingerspelling Recognition. Proceedings of the IEEE International Conference on Computer Vision Workshops (pp. 1114–1119). (available at http://info.ee.surrey.ac.uk/Personal/N.Pugeault/index.php?section=FingerSpellingDataset).

[3] Vieriu, R., Goras, B. & Goras, L. (2011). On HMM Static Hand Gesture Recognition. Proceedings of International Symposium on Signals, Circuits and Systems (pp. 1–4). Iasi, Romania.

[4] Kaaniche, M. & Bremond, F. (2009). Tracking HOG Descriptors for Gesture Recognition. Proceedings of the Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance (pp. 140–145). Genova, Italy.

[5] Wachs, J. P., Kölsch, M., Stern, H., & Edan, Y. (2011). Vision-based Hand-gesture Applications. Communications of the ACM, 54(2), 60–71.

NJIT Department of Electrical and Computer Engineering March 5, 201317

Biography

Joseph Picone received his Ph.D. in Electrical Engineering in 1983from the Illinois Institute of Technology. He is currently a professor in the Department of Electrical and Computer Engineering at Temple University. He has spent significant portions of his career in academia (MS State), research (Texas Instruments, AT&T) and the government (NSA), giving him a very balanced perspective on the challenges of building sustainable R&D programs.

His primary research interests are machine learning approaches to acoustic modeling in speech recognition. For almost 20 years, his research group has been known for producing many innovative open source materials for signal processing including a public domain speech recognition system (see www.isip.piconepress.com).

Dr. Picone’s research funding sources over the years have included NSF, DoD, DARPA as well as the private sector. Dr. Picone is a Senior Member of the IEEE, holds several patents in human language technology, and has been active in several professional societies related to HLT.